Adequacy of prostate cancer prevention and screening recommendations provided by an artificial intelligence-powered large language model.
Giuseppe ChiarelliAlex StephensMarco FinatiGiuseppe Ottone CirulliEdoardo BeatriciDejan K FilipasSohrab AroraShane TinsleyMahendra BhandariGiuseppe CarrieriQuoc-Dien TrinhAlberto BrigantiFrancesco MontorsiGiovanni LughezzaniNicolò BuffiCraig RogersFiras AbdollahPublished in: International urology and nephrology (2024)
GPT-4 displayed superior accuracy, clarity, conciseness, and readability than GPT-3.5. Though prompts influenced the quality response in both GPTs, their impact was significant only for clarity.